Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (l
    -0.08
    	usage
    -0.07
    _vc
    -0.07
    (m
    -0.07
    +:
    -0.07
    _requested
    -0.07
     ----------------------------------------------------------------
    -0.06
    Basket
    -0.06
    (i
    -0.06
    (bg
    -0.06
    POSITIVE LOGITS
    ี้
    0.07
    �
    0.07
    olta
    0.07
     현대
    0.07
    endant
    0.06
     Gör
    0.06
     Slip
    0.06
    (reordered
    0.06
    ovah
    0.06
    ”。↵↵
    0.06
    Act Density 0.003%

    No Known Activations